Cancer Imaging最新文献

{"title":"Multidisciplinary attitudes towards LLM-structured oncologic CT reports: a prospective fixed-sequence questionnaire study.","authors":"Felix Busch, Alexander W Marka, Lilly F Wingberg, Philipp Prucker, Su Hwan Kim, Quirin Strotzer, Christina Schmidt, Jacqueline Lammert, Kai J Borm, Jan Peeken, Marcus R Makowski, Lisa C Adams, Keno K Bressem","doi":"10.1186/s40644-026-01137-2","DOIUrl":"10.1186/s40644-026-01137-2","url":null,"abstract":"<p><strong>Objectives: </strong>Large language models (LLMs) can automate the conversion of radiologic free text into structured reports, but multidisciplinary reader preferences for the resulting output remain insufficiently studied. This prospective, two-phase, fixed-sequence within-participant study evaluated reader assessments of LLM-structured versus conventional free-text oncologic CT reports.</p><p><strong>Material & methods: </strong>A paired convenience sample of radiologists, radiology technologists, oncologists, and medical students was recruited between May and November 2025. In Phase 1, participants rated 5 free-text oncologic CT reports for readability and comprehension (3 items), oncologic information quality (5 items), and clinical utility (4 items) on a 9-point Likert scale. After a washout of at least 4 weeks, participants rated the LLM-structured version generated by Llama-4-Scout-17B-16E-Instruct.</p><p><strong>Results: </strong>Sixty-six paired participants (24 medical students, 22 radiologists, 12 radiology technologists, 8 oncologists) were included (mean [standard deviation] age, 30.5 [7.6] years; 37 [56.1%] female). Structured reports showed significantly higher odds of agreement for 11 of 12 items (odds ratio [OR] range, 1.70-4.81), with strongest effects for clinical utility (OR, 4.81; 95% CI, 3.24-7.15), information findability (OR, 4.31; 95% CI, 3.12-5.96), recommendation clarity (OR, 4.14; 95% CI, 2.95-5.83), and patient communication suitability (OR, 3.45; 95% CI, 2.59-4.60). Radiology technologists showed significantly higher ratings for all 12 items, radiologists for 6, students for 7, and oncologists for none.</p><p><strong>Conclusion: </strong>In this single-center paired sample, LLM-structured oncologic CT reports received higher reader ratings than conventional free-text reports across most evaluated dimensions, with the largest differences observed for information findability and clinical utility. These findings support further evaluation of radiologist-supervised LLM-assisted report structuring, including formal source-to-output validation and randomized multicenter assessment, before clinical implementation.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13651054/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149134740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CT radiomics showed no improvement beyond volume dynamics for early lesion-level size response to immunotherapy in metastatic melanoma.","authors":"Seval Akbal, Johan Constantin Schepers, Paul V Op Gen Oorth, Vincent Bleymehl, Moritz Schroth, Felix Winneknecht, Devayani Machiraju, Julius C Holzschuh, Kevin S Zhang, Sebastian Wohlfeil, Isabelle Ayx, Stefan O Schoenberg, Heinz-Peter Schlemmer, Jessica C Hassel, Lukas T Rotkopf","doi":"10.1186/s40644-026-01135-4","DOIUrl":"https://doi.org/10.1186/s40644-026-01135-4","url":null,"abstract":"<p><strong>Background: </strong>We evaluated whether CT intensity and texture radiomics provide predictive value beyond simple volume dynamics for lesion-level response prediction in metastatic melanoma treated with immune checkpoint inhibitors.</p><p><strong>Methods: </strong>We conducted a retrospective multicenter study including 158 patients (1,626 lesions) from an internal cohort (n = 129 patients with standardized protocols) and an external cohort (n = 29 patients with heterogeneous protocols). The primary endpoint was binary lesion-level size response (clinical benefit vs. progressive disease) at the second follow-up. We trained and compared Random Forest classifiers to predict this endpoint using clinical variables, volumetric features, radiomics, and combined predictors derived from baseline and first follow-up imaging. Models were trained on the internal cohort using patient-grouped cross-validation and applied unchanged to the external cohort. Paired differences in AUC were assessed against a ± 0.05 equivalence margin.</p><p><strong>Results: </strong>Baseline-only prediction of first follow-up response was near chance for all models. For predicting response at second follow-up, the volumetric model achieved an internal AUC of 0.84 [95% CI 0.78-0.88] and the radiomics model 0.86 [0.81-0.90]. In the external cohort, with 12 progression events, the volumetric and radiomics models achieved AUCs of 0.68 [0.50-0.85] and 0.68 [0.51-0.88], with no significant difference between any models. Organ-specific analysis showed no significant improvement from adding radiomics for any lesion site. Across all 288 radiomic features, the median absolute correlation with lesion volume was 0.37. Sensitivity analyses contained small or borderline gains that did not replicate externally.</p><p><strong>Conclusions: </strong>Volumetric features capture the primary predictive information for early lesion-level response, and CT radiomics showed no conclusive improvement over volume dynamics. Confirmation in larger independent cohorts is required before radiomic signatures can be recommended for this task.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13632448/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149104598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Proceedings of the 25th International Cancer Imaging Society Meeting and Annual Teaching Course.","authors":"","doi":"10.1186/s40644-026-01094-w","DOIUrl":"10.1186/s40644-026-01094-w","url":null,"abstract":"","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 Suppl 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13587269/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148988259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic performance of AI-powered prostate MRI against biopsy ground truth: quasi-continuous risk scoring versus fixed PI-RADS thresholds.","authors":"Nadine Bayerl, Joel Appel, Maximilian Schmidt, Alexander Cavallaro, Robert Grimm, Heinrich von Busch, Bernd Wullich, Arndt Hartmann, Michael Schlicht, Michael Uder, Matthias S May, Stephan Ellmann","doi":"10.1186/s40644-026-01126-5","DOIUrl":"10.1186/s40644-026-01126-5","url":null,"abstract":"<p><strong>Background: </strong>Multiparametric prostate MRI is central to prostate cancer (PCa) diagnostics, yet PI-RADS interpretation suffers from inter-reader variability. This study aimed to evaluate a commercial AI algorithm for cancer detection in prostate MRI against histopathology, comparing its standard PI-RADS classification with its quasi-continuous Level-of-Suspicion (LoS) score as decision variables.</p><p><strong>Methods: </strong>In this retrospective single-center study, 122 mpMRI examinations, each followed by systematic and/or fusion-targeted biopsy, were analyzed. Histopathology served as the reference standard for any PCa (Gleason ≥ 6) and clinically significant PCa (csPCa; Gleason ≥ 7). Diagnostic performance of the algorithm's PI-RADS and LoS outputs was assessed by ROC analysis. AUCs were compared using DeLong's test. The Youden-optimal LoS cutoff was determined, its optimism was quantified by bootstrap internal validation, and the calibration of the LoS score was assessed after logistic recalibration.</p><p><strong>Results: </strong>For csPCa, PI-RADS yielded an AUC of 0.833 (95% CI: 0.764-0.901), versus 0.882 (95% CI: 0.820-0.943) for the LoS score (p = 0.106). At PI-RADS ≥ 4, sensitivity was 94.7% and specificity 63.1%. The Youden-optimal LoS cutoff was 81. At this exploratory threshold, sensitivity remained 94.7% while specificity was 70.8%, with positive and negative predictive values of 74.0% and 93.9%, respectively. Bootstrap internal validation indicated modest optimism, with corrected estimates of 92.9% for sensitivity and 69.1% for specificity. After logistic recalibration, the bootstrap-corrected calibration slope was 0.98 with an intercept of -0.01.</p><p><strong>Conclusion: </strong>In this retrospective single-center cohort, the AI algorithm achieved high diagnostic accuracy for csPCa. Its quasi-continuous LoS score provided an operating point combining high sensitivity with numerically higher specificity than the PI-RADS ≥ 4 threshold. Neither this difference (exact McNemar p = 0.063) nor the difference in AUC between the two classifiers (p = 0.106) reached statistical significance, so the finding should be regarded as a promising trend rather than a demonstrated advantage. Prospective confirmation is required before AI-assisted standardized interpretation is integrated into prostate MRI workflows on this basis.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580003/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148975590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative PCCT spectral parameters for noninvasive prediction of EGFR status and its subtypes in lung adenocarcinoma.","authors":"Jiazhong Ren, Yong Huang, Linfeng Li, Yuqin Jin, Yong Yin","doi":"10.1186/s40644-026-01122-9","DOIUrl":"https://doi.org/10.1186/s40644-026-01122-9","url":null,"abstract":"<p><strong>Objective: </strong>To investigate the non-invasive predictive value of quantitative spectral parameters from photon-counting computed tomography (PCCT) for epidermal growth factor receptor (EGFR) mutation status and its predominant subtypes (19Del and L858R) in patients with lung adenocarcinoma.</p><p><strong>Methods: </strong>A total of 72 patients with pathologically confirmed lung adenocarcinoma who underwent pretreatment PCCT were retrospectively enrolled. Arterial and venous CT attenuation values at 40 keV, 70 keV, and 100 keV (A/V-40 keV, A/V-70 keV, A/V-100 keV) were measured on virtual monoenergetic images, while arterial/venous iodine concentration (IC) and dual-energy index (DEI) of lesions were measured on iodine maps and spectral post-processing (SPP) images, respectively. Normalized iodine concentration (NIC) and spectral curve slope (λHU) were further calculated. Receiver operating characteristic (ROC) curve analysis and binary logistic regression were performed to evaluate the predictive performance and independent predictive value of PCCT parameters for discriminating EGFR-mutant vs. wild-type tumors, as well as 19Del vs. L858R subtypes.</p><p><strong>Results: </strong>Of 72 patients, 37 (51.4%) harbored EGFR mutations, which correlated with female sex, never-smoking, reduced NSE, and lower monocyte count. The EGFR-mutant group showed significantly higher A-70 keV, A-100 keV, A-DEI, V-40 keV, V-70 keV, V-100 keV, V-λHU and V-DEI (all P < 0.05). Logistic regression identified female sex (P = 0.019, OR = 5.714, 95% CI: 1.336-24.442) and A-100 keV (P = 0.044, OR = 0.543, 95% CI: 0.300-0.983) as independent predictors. ROC analysis with bootstrap validation yielded: clinical model AUC 0.767 (optimism-corrected 0.762); PCCT model AUC 0.713 (optimism-corrected 0.707); combined model AUC 0.771 (optimism-corrected 0.768) (all P < 0.001). Between 19Del (n = 15) and L858R (n = 17) subgroups, A-40 keV and A-DEI showed significant discriminative performance in ROC analysis, with AUCs of 0.694 and 0.704 (optimism-corrected AUCs: 0.688 and 0.697, respectively).</p><p><strong>Conclusions: </strong>Quantitative PCCT spectral parameters enable non-invasive prediction of EGFR mutation status and preliminary differentiation between 19Del and L858R subtypes in lung adenocarcinoma, though subtype-related findings require validation in larger cohorts. Female sex and A-100 keV are independent predictive factors. The combined model yielded a numerically higher AUC without statistically significant superiority, and PCCT parameters may provide auxiliary imaging evidence to inform individualized targeted therapy decisions in lung adenocarcinoma.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13625330/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149104609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"¹⁸F-FDG PET/CT metabolic parameter to predict pathological complete response and survival after neoadjuvant immunotherapy plus chemoradiotherapy in resectable esophageal squamous cell carcinoma.","authors":"Jichen Yang, Li Ma, Xiaoming Zhao, Peng Jin, Xue Meng, Wenxing Du, Zhe Wu, Wenjie Jiao, Wenfeng Yang","doi":"10.1186/s40644-026-01118-5","DOIUrl":"10.1186/s40644-026-01118-5","url":null,"abstract":"<p><strong>Background: </strong>Neoadjuvant immunotherapy plus chemoradiotherapy (nICRT) for esophageal squamous cell carcinoma (ESCC) received increasing attention because of high pathological complete response (pCR) rate. Accurately assessing residual disease after nICRT is beneficial for dynamic monitoring of patients. This exploratory, single-arm, phase II clinical study aimed to evaluate the diagnostic efficacy of ¹⁸F-FDG PET/CT for achieving pCR after nICRT for ESCC, and its prognostic value for survival.</p><p><strong>Methods: </strong>From January 12, 2021 to February 21, 2023, a total of 21 resectable ESCC patients receiving nICRT were enrolled and underwent baseline PET/CT scans (scan-1) and surgery. 19 patients underwent scans (scan-2) before surgery. The recorded PET/CT parameters included maximum, mean, and peak standardized uptake values (SUVmax, SUVmean, and SUVpeak), metabolic tumor volume (MTV), and total lesion glycolysis (TLG). The diagnostic performance of PET/CT parameters was analyzed between the patients with pCR of the primary tumor (pCR-tu) and non-pCR-tu. The Cox regression and Kaplan-Meier method were performed for multivariable analysis and survival analyses, respectively.</p><p><strong>Results: </strong>13(61.9%) achieved pCR-tu after nICRT among the 21 participants. None of the single metabolic parameters of primary tumor were significant predictors of pCR-tu (all p > 0.05). SUVmax2 of lymph nodes (Ln) has diagnostic value for lymph nodes metastasis (p < 0.01), the area under the curve (AUC), sensitivity and specificity were 0.812, 77.8% and 76.9%, respectively. The 3-year overall survival (OS) and disease-free survival (DFS) rates were 76.2% and 66.7%, respectively. Univariate Cox regression indicated that OS and DFS were correlated with the postoperative ypN stage, ypTNM stage, pCR, pCR-tu, SUVmax2, and LnSUVmax2. Long rank analysis showed that patients with a cutoff value of ≥12.4 for SUVmax2 and of ≥7.9 for LnSUVmax2 had poorer OS and DFS. However, multivariate Cox regression showed that the parameters mentioned above were not independent prognostic factors for OS and DFS.</p><p><strong>Conclusions: </strong>None of the single metabolic parameters of the primary tumor were significant predictors of pCR-tu. LnSUVmax2 has diagnostic value for lymph nodes metastasis. The patients with SUVmax2 ≥ 12.4 and LnSUVmax2 ≥ 7.9 had poorer OS and DFS, but they are not independent prognostic factors, which needs to be confirmed by larger scale clinical studies.</p><p><strong>Trial registration: </strong>NCT05323890. Registered on April 5, 2022. Retrospectively registered.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13584425/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148988252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heterogeneous treatment response in metastatic breast cancer: discordance between FDG-PET and CT classification.","authors":"Vilma Landfors Andersson, Kristin Johnson, Ida Skarping","doi":"10.1186/s40644-026-01119-4","DOIUrl":"10.1186/s40644-026-01119-4","url":null,"abstract":"<p><strong>Background: </strong>Heterogeneous treatment response, characterized by simultaneous regression of some lesions and progression of others within the same patient, is increasingly recognized in metastatic breast cancer (mBC) and may reflect biological heterogeneity. However, this response pattern is not captured by current response assessment frameworks. We aimed to determine the prevalence of heterogeneous treatment response on FDG-PET and mixed response on CT during mBC systemic therapy.</p><p><strong>Methods: </strong>This retrospective study included 51 female patients with mBC, treated between November 2017 and November 2025, each undergoing ≥ 2 FDG-PET/CT scans. Response was assessed according to RECIST 1.1 (CT) and PERCIST (FDG-PET), with using study‑specific definitions for heterogeneous/mixed response informed by literature.</p><p><strong>Results: </strong>Heterogeneous metabolic response was observed in 30% of all follow‑up FDG‑PET examinations (40/132). These examinations accounted for 60% (40/67) of the scans classified as progressive metabolic disease (PMD) according to PERCIST. Among CT-examinations, 65 of 141 (46%) follow-up examinations had measurable disease; none of these scans (0/65, 0%) fulfilled the mixed response criteria.</p><p><strong>Conclusion: </strong>In this real-world cohort of mBC undergoing systemic therapy, FDG-PET identified heterogeneous treatment response in a substantial proportion of patients; however, under current PERCIST criteria, these cases were uniformly classified as PMD. In contrast, using RECIST-inspired criteria, CT did not classify any patient as mixed response. These findings suggest that existing frameworks may not fully capture intra-patient response heterogeneity. As heterogeneous response is not an established PERCIST response category, further work is needed to determine how such patterns should be defined and incorporated into future response assessment frameworks.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13520370/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148839464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Krenning score enhances integrated biomarker models for survival prediction in PRRT-treated GEP-NET: a retrospective cohort study.","authors":"Christian A Dascalescu, Felix L Herr, Ricarda Ebner, Victoria Fusch, Moritz L Schnitzer, Matthias P Fabritius, Christine Schmid-Tannwald, Mathias J Zacherl, Vera Wenter, Matthias Brendel, Adrien Holzgreve, Christoph J Auernhammer, Christine Spitzweg, Thomas Knösel, Tanja Burkard, Jens Ricke, Johannes Rübenthaler, Maurice M Heimer, Gabriel T Sheikh, Rudolf A Werner, Konrad Klimek, Clemens C Cyran","doi":"10.1186/s40644-026-01113-w","DOIUrl":"10.1186/s40644-026-01113-w","url":null,"abstract":"<p><strong>Background: </strong>Purpose of this study is to evaluate the value of a routinely available baseline SSTR-PET imaging parameter, the Krenning score (KS), within integrated biomarker models for overall survival prediction in gastroenteropancreatic neuroendocrine tumor (GEP-NET) patients undergoing peptide receptor radionuclide therapy (PRRT).</p><p><strong>Methods: </strong>We retrospectively analyzed 178 patients with GEP-NET who underwent PRRT. At baseline, the KS, clinical, histopathological, and laboratory parameters were integrated and correlated with OS. OS predictors were identified using univariate Cox regression analysis and incorporated into multivariate models. Model performance was assessed using the concordance index (C-index) and Akaike information criterion (AIC).</p><p><strong>Results: </strong>In univariate analysis, the following parameters were significantly associated with shorter OS: KS 3 vs. KS 4 (p = 0.042), CgA > 155 ng/mL (p = 0.003), NSE > 35 ng/mL (p = 0.042), BMI < 18.5 kg/m² (p = 0.017), CRP > 0.5 mg/dL (p = 0.045), albumin < 4.1 g/dL (p = 0.017), and Hb < 12 g/dL (p = 0.017). The multivariate Cox regression model including KS, hemoglobin, and NSE showed the lowest AIC (C-index = 0.64, CI: 0.57-0.71; AIC = 527.60), while the model incorporating BMI, hemoglobin, and CgA demonstrated the highest C-index (C-index = 0.66, CI: 0.60-0.72; AIC = 582.82).</p><p><strong>Conclusion: </strong>Integrated baseline biomarker models combining clinical, laboratory, and imaging parameters may support overall survival risk stratification in GEP-NET patients undergoing PRRT. Incorporation of the routinely available Krenning score contributed to one of the best-performing parsimonious exploratory multivariable models, suggesting that accessible molecular imaging parameters may complement established baseline biomarkers. These exploratory findings require validation in larger, preferably multicenter, independent cohorts before clinical implementation.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13505048/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148817533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dual-energy CT extracellular volume fraction for predicting the chemotherapeutic response in pancreatic ductal adenocarcinoma.","authors":"Shuai Ming, Peng Cheng, Yuanyuan Ruan, Dan Shi, Bin Wang, Jingyu Li, Wuyang Zhang, Min Wang, Hongji Zhu, Yadi Zhang, Chenglin Zhu, Ben Zhao, Aiyun Sun, Wei Wei","doi":"10.1186/s40644-026-01110-z","DOIUrl":"10.1186/s40644-026-01110-z","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to investigate the value of the extracellular volume fraction (ECV) derived from dual-energy computed tomography (DECT) in predicting the chemotherapeutic response in patients with pancreatic ductal adenocarcinoma (PDAC).</p><p><strong>Methods: </strong>This study included 112 patients with pathologically confirmed PDAC who underwent dynamic contrast-enhanced DECT prior to chemotherapy. Iodine concentrations were measured on delayed-phase iodine maps within the tumor and aorta, and the ECV was calculated on the basis of the iodine concentration. Treatment response to chemotherapy was assessed according to the RECIST 1.1 criteria. Univariate and multivariate analyses were conducted to identify predictors of treatment response. Receiver operating characteristic (ROC) curves were used to evaluate the predictive performance of the identified variables.</p><p><strong>Results: </strong>The tumor ECV was significantly lower in the response group (23.64%) than in the nonresponse group (38.13%)(P < 0.001). The tumor ECV was also an independent predictor of poor response to chemotherapy (OR = 1.259; P = 0.023) and had the highest diagnostic value, with an area under the curve (AUC) value of 0.83, significantly outperforming the venous phase iodine concentration (IC_VP; AUC = 0.73). When the optimal cutoff value of the ECV was used (31.8%), the sensitivity, specificity and accuracy for predicting the response group were 81.0%, 70.4% and 75.9%, respectively. The Delong test revealed a significant difference in the AUC value between the ECV model and the IC_VP model (P = 0.026).</p><p><strong>Conclusions: </strong>DECT-derived ECV represents a promising noninvasive biomarker for predicting chemotherapy response in PDAC patients, with lower ECV values potentially indicating a more favorable therapeutic outcome.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13520392/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148839455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting ki-67 expression in breast cancer via transformer and multiple instance learning on DCE-MRI.","authors":"Yiying Cao, Mianlei Lin, Yanshan Ouyang, Yingning Wu, Caitao Zhao, Qian Wu, Deqiu Teng, Nanxuan He, Xiao Zhong, Junneng Yang","doi":"10.1186/s40644-026-01100-1","DOIUrl":"https://doi.org/10.1186/s40644-026-01100-1","url":null,"abstract":"<p><strong>Background: </strong>Accurate assessment of Ki-67 expression levels in breast cancer is crucial for determining prognosis and making informed treatment decisions. Current immunohistochemical methods relying on needle biopsy introduce sampling errors due to tumor spatial heterogeneity, making the development of non-invasive, precise preoperative prediction methods of significant clinical importance. This study aims to explore and compare advanced deep learning models based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for noninvasive assessment of Ki-67 expression.</p><p><strong>Methods: </strong>This retrospective study analyzed preoperative DCE-MRI data from 308 patients with histologically confirmed breast cancer. Adjacent slices centered on the tumor's most significant cross-section were obtained to create a 2.5-dimensional (2·5D) dataset. We innovatively developed two deep learning models using the same dataset (1): a Multi-Instance Learning (MIL) model that combines slice-level predictive features with Predictive Likelihood Histogram (PLH) and Bag-of-Words (BoW) techniques (2); a Transformer-based fusion model that directly captures global contextual relationships between slices via self-attention mechanisms. The predictive performance of both models was systematically compared with traditional radiomics and clinical models.</p><p><strong>Results: </strong>On an independent test set, the Transformer fusion model demonstrated optimal predictive performance with an area under the curve (AUC) of 0.875, achieving accuracy, sensitivity, and specificity of 0.839, 0.848, and 0.833, respectively. The MIL model ranked second (AUC = 0.825), with both models significantly outperforming traditional radiomics models (AUC = 0.698) and clinical models (AUC = 0.648).</p><p><strong>Conclusions: </strong>Deep learning models based on 2·5D DCE-MRI, especially Transformer models that achieve global feature fusion through self-attention mechanisms, can effectively and non-invasively predict Ki-67 expression status in breast cancer, surpassing traditional methods. This model shows potential as a reliable tool to help clinicians accurately assess tumor proliferation activity before surgery.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"26 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13488245/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148788818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}